agentleFS
CodeCaroSCodeCaroS/MythOs_Aegis/.agents/skills/tdd/SKILL.md

tdd

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

Implement features and bug fixes in small red-green slices using behavior-focused tests at existing public seams. Use when the user requests TDD, test-first work, red-green-refactor, regression coverage, or a fix that must leave a runnable guard.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture-learning-tools, design-frontend-dev and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • The-Vibe-CompanySkill

    capture-learning-tools

    Turn technical conversations, bugs, CI failures, review comments,

    Also in 5 projects that use this

  • The-Vibe-CompanySkill

    design-frontend-dev

    Clean Impeccable frontend design skill. Use when the user wants to

    Also in 5 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • jaydubya818Skill

    figure-it-out

    Use when novel or multi-phase work needs an auditable workflow and no narrower playbook fits.

    Also in 54 projects that use this

  • jaydubya818Skill

    principle-laziness-protocol

    Apply when a refactor is adding wrappers or abstractions instead of simplifying.

    Also in 45 projects that use this

  • +2 more from The-Vibe-Company
  • +5 more from jaydubya818

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 186 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use one vertical slice at a time:

    line 17
  2. Distinctive:

    Read the real flow and every caller of the behavior being changed.

    line 19
  3. Distinctive:

    Write one test that fails for the right reason.

    line 22
  4. Distinctive:

    Run the focused test, then the nearest broader gate.

    line 24
  5. Distinctive:

    Use independent expected values, not the production algorithm repeated in the test.

    line 31
  6. Distinctive:

    Do not assert private methods, internal call order, or implementation-specific collaborator counts.

    line 33
  7. Distinctive:

    Keep the test that proves the reported failure fixed.

    line 35
  8. Distinctive:

    Do not pause for seam approval when the repository and request make the public boundary clear.

    line 37
  9. Distinctive:

    Before step 4, check whether the seam touches authentication, authorization, tenant isolation, or secrets.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 186 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Test-Driven Development

Use one vertical slice at a time:

  1. Read the real flow and every caller of the behavior being changed.
  2. If acceptance criteria or a specification already exist for this change, read them first; the failing test must prove one of those criteria. If none exist and the change is more than a small, obvious fix, state the acceptance criterion the test will prove before writing it.
  3. Select the narrowest existing public seam that exposes the bug or capability.
  4. Write one test that fails for the right reason.
  5. Make the smallest root-cause change that passes it.
  6. Run the focused test, then the nearest broader gate.
  7. Refactor only if the passing code now contains real duplication or confusion.
  8. Repeat only for the next distinct behavior.

Test Quality

  • Assert observable behavior through public interfaces.
  • Use independent expected values, not the production algorithm repeated in the test.
  • Mock only external or nondeterministic boundaries; prefer a real test database or filesystem when cheap and isolated.
  • Do not assert private methods, internal call order, or implementation-specific collaborator counts.
  • For UI flows, cover interactions and state transitions: validation, empty/error states, duplicate submissions, permissions, and reload persistence where relevant.
  • Keep the test that proves the reported failure fixed.

Do not pause for seam approval when the repository and request make the public boundary clear. Ask only when different seams would materially change scope or compatibility.

Before step 4, check whether the seam touches authentication, authorization, tenant isolation, or secrets. If so, follow decision-criticality-gate's Hard Escalation Rules and get approval before implementing, rather than proceeding straight to the green step.

Adapted for MythOs Aegis from mattpocock/skills tdd.

Shared output profile

Compose the execution profile from output-templates. Report the red failure, green change, exact test result, and any verification limit. Preserve stricter domain rules above, omit empty components, and never fill a component with invented evidence.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.